© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 34181
    Prev
    Next
    INDEX
    Explanations

    names ending in -am/-er/-ier/-um

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    bcywinski/Olmo-3-32B-Base-SAE/saes_allenai_Olmo-3-1125-32B_batch_top_k/resid_post_layer_32
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     beb
    -0.11
     bm
    -0.10
     b
    -0.10
     bq
    -0.09
     Bounty
    -0.09
    byn
    -0.09
     BPM
    -0.09
     Bry
    -0.09
    adera
    -0.09
     Barcl
    -0.09
    POSITIVE LOGITS
    chia
    0.10
    hea
    0.09
     funnel
    0.09
     reco
    0.08
     tricks
    0.08
     lect
    0.08
    oze
    0.08
    lier
    0.08
    ram
    0.08
    oland
    0.08
    Activations Density 0.228%

    No Known Activations